© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 95256
    Prev
    Next
    INDEX
    Explanations

    numeric values representing quantities or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overall
    -0.06
    Yes
    -0.06
    Ãłnh
    -0.06
     such
    -0.06
    1
    -0.06
    ampie
    -0.06
     Grove
    -0.06
     indeed
    -0.06
    YES
    -0.05
     Yes
    -0.05
    POSITIVE LOGITS
    ston
    0.08
    agues
    0.08
    utterstock
    0.08
    ñana
    0.08
    948
    0.07
    imag
    0.07
    AGES
    0.07
    STANCE
    0.07
    987
    0.07
    uil
    0.07
    Activations Density 0.040%

    No Known Activations